Files
headquarter/apps/api/src/services/terminal_session.py
T
Fusion 0cb2eefd29 fix: send SIGWINCH to docker exec process for container terminal resize
Instead of sending stty commands through the user's terminal session
(which causes 'inappropriate ioctl' errors), send SIGWINCH signal to
the docker exec process on the host. Docker exec should forward this
to the container process, causing the shell to re-read its terminal size.

This avoids:
- Visible stty commands in the terminal
- ioctl errors from stty
- Interference with user's shell session
2026-05-24 20:47:14 +02:00

238 lines
8.1 KiB
Python

"""Terminal session management for tool instances."""
import asyncio
import logging
import os
import pty
import select
import signal
import struct
import fcntl
import time
import uuid
from collections import deque
from typing import Any
logger = logging.getLogger(__name__)
class TerminalSession:
"""Manages a single terminal session connected to a docker container.
Supports persistent sessions that survive WebSocket disconnections.
Multiple WebSocket connections can attach/detach from the same session.
"""
# Circular buffer size (10KB)
BUFFER_SIZE = 10 * 1024
# Idle timeout in seconds (30 minutes)
IDLE_TIMEOUT = 30 * 60
def __init__(self, session_id: str, instance_id: uuid.UUID, container_id: str) -> None:
self.session_id = session_id
self.instance_id = instance_id
self.container_id = container_id
self.process: asyncio.subprocess.Process | None = None
self._closed = False
self._master_fd: int | None = None
self._slave_fd: int | None = None
# Circular buffer for output replay
self._output_buffer: deque[bytes] = deque(maxlen=self.BUFFER_SIZE)
self._buffer_size = 0
# WebSocket connections
self._websockets: set[Any] = set()
# Activity tracking
self.last_activity = time.time()
# Terminal size
self._cols = 80
self._rows = 24
async def start(self) -> None:
"""Start the docker exec process with a shell using a PTY."""
# Create a pseudo-terminal on the host
self._master_fd, self._slave_fd = pty.openpty()
# Set the terminal size initially
self._set_terminal_size(self._cols, self._rows)
logger.info(f"Starting terminal session {self.session_id} for container {self.container_id} with initial size {self._cols}x{self._rows}")
# Start docker exec with the slave fd as stdin/stdout/stderr
# Using -it because the slave fd IS a TTY
self.process = await asyncio.create_subprocess_exec(
"docker",
"exec",
"-it",
"-e",
"TERM=xterm",
self.container_id,
"bash",
"-il",
stdin=self._slave_fd,
stdout=self._slave_fd,
stderr=self._slave_fd,
)
# Close slave fd in parent process
os.close(self._slave_fd)
self._slave_fd = None
self.last_activity = time.time()
def _set_terminal_size(self, cols: int, rows: int) -> None:
"""Set the terminal size using TIOCSWINSZ."""
if self._master_fd is None:
logger.warning("Cannot resize: master_fd is None (session not started)")
return
# TIOCSWINSZ = 0x5414 on Linux
TIOCSWINSZ = 0x5414
size = struct.pack('HHHH', rows, cols, 0, 0)
try:
fcntl.ioctl(self._master_fd, TIOCSWINSZ, size)
logger.info(f"Resized PTY to {cols}x{rows} (fd={self._master_fd})")
except (OSError, IOError) as e:
logger.error(f"Failed to resize PTY: {e}")
async def read_output(self) -> bytes:
"""Read output from the PTY master and store in buffer."""
if self._master_fd is None or self._closed:
return b""
try:
# Use select to check if data is available
readable, _, _ = select.select([self._master_fd], [], [], 0.1)
if readable:
data = os.read(self._master_fd, 4096)
if data:
self._add_to_buffer(data)
self.last_activity = time.time()
return data
return b""
except (OSError, IOError, ValueError):
return b""
def _add_to_buffer(self, data: bytes) -> None:
"""Add data to circular buffer, maintaining size limit."""
self._output_buffer.append(data)
self._buffer_size += len(data)
# Trim if exceeds max size
while self._buffer_size > self.BUFFER_SIZE and self._output_buffer:
removed = self._output_buffer.popleft()
self._buffer_size -= len(removed)
def get_buffer(self) -> bytes:
"""Get buffered output for replay."""
return b"".join(self._output_buffer)
async def write_input(self, data: bytes) -> None:
"""Write input to the PTY master."""
if self._master_fd is None or self._closed:
return
try:
os.write(self._master_fd, data)
self.last_activity = time.time()
except (OSError, IOError):
pass
async def resize(self, cols: int, rows: int) -> None:
"""Resize the terminal."""
if self._closed:
logger.warning("Cannot resize: session is closed")
return
# Only resize if dimensions actually changed
if cols == self._cols and rows == self._rows:
return
self._cols = cols
self._rows = rows
logger.info(f"resize() called for session {self.session_id}: {cols}x{rows}")
self._set_terminal_size(cols, rows)
# Docker exec -it creates its own PTY inside the container,
# so host PTY resize doesn't propagate to the container shell.
# Send SIGWINCH to the docker exec process on the host.
# Docker exec forwards signals to the container process, which should
# cause the container's shell to re-read its terminal size.
if self.process and self.process.pid:
try:
os.kill(self.process.pid, signal.SIGWINCH)
logger.debug(f"Sent SIGWINCH to docker exec process {self.process.pid} for session {self.session_id}")
except ProcessLookupError:
logger.warning(f"docker exec process {self.process.pid} not found for session {self.session_id}")
except Exception as e:
logger.warning(f"Failed to send SIGWINCH: {e}")
async def reset(self) -> None:
"""Reset the session by killing the process and clearing state."""
await self.close()
self._closed = False
self._output_buffer.clear()
self._buffer_size = 0
self._websockets.clear()
self.process = None
self._master_fd = None
self._slave_fd = None
async def close(self) -> None:
"""Close the session and cleanup."""
if self._closed:
return
self._closed = True
if self._master_fd is not None:
try:
os.close(self._master_fd)
except OSError:
pass
self._master_fd = None
if self.process is not None:
try:
self.process.kill()
await asyncio.wait_for(self.process.wait(), timeout=2.0)
except (asyncio.TimeoutError, ProcessLookupError):
pass
def is_alive(self) -> bool:
"""Check if the session process is still running."""
if self.process is None:
return False
return self.process.returncode is None
def is_idle(self) -> bool:
"""Check if the session has been idle for too long."""
if self._websockets:
return False
return time.time() - self.last_activity > self.IDLE_TIMEOUT
def attach_websocket(self, websocket: Any) -> None:
"""Attach a WebSocket to this session."""
self._websockets.add(websocket)
self.last_activity = time.time()
def detach_websocket(self, websocket: Any) -> None:
"""Detach a WebSocket from this session."""
self._websockets.discard(websocket)
def has_websockets(self) -> bool:
"""Check if any WebSockets are attached."""
return len(self._websockets) > 0
async def send_to_all(self, data: bytes) -> None:
"""Send data to all attached WebSockets."""
dead_sockets = set()
for ws in self._websockets:
try:
await ws.send_bytes(data)
except Exception:
dead_sockets.add(ws)
# Clean up dead sockets
for ws in dead_sockets:
self._websockets.discard(ws)